Sean Knight

Sean Knight, Navjot Gadda

In recent years, there has been increasing interest in developing models and tools to address the complex patterns of connectivity found in brain tissue. Specifically, this is due to a need to understand how emergent properties emerge from these network structures at multiple spatiotemporal scales. We argue that computational models are key tools for elucidating the possible functionalities that can emerge from interactions of heterogeneous neurons connected by complex networks on multi-scale temporal and spatial domains. Here we review several classes of models including spiking neurons, integrate and fire neurons with short term plasticity (STP), conductance based integrate-and-fire models with STP, and population density neural field (PDNF) models using simple examples with emphasis on neuroscience applications while also providing some potential future research directions for AI. These computational approaches allow us to explore the impact of changing underlying mechanisms on resulting network function both experimentally as well as theoretically. Thus we hope these studies will inform future developments in artificial intelligence algorithms as well as help validate our understanding of brain processes based on experiments in animals or humans.

Soukayna Mouatadid, Paulo Orenstein, Genevieve Flaspohler et al.

Subseasonal forecasting of the weather two to six weeks in advance is critical for resource allocation and advance disaster notice but poses many challenges for the forecasting community. At this forecast horizon, physics-based dynamical models have limited skill, and the targets for prediction depend in a complex manner on both local weather variables and global climate variables. Recently, machine learning methods have shown promise in advancing the state of the art but only at the cost of complex data curation, integrating expert knowledge with aggregation across multiple relevant data sources, file formats, and temporal and spatial resolutions. To streamline this process and accelerate future development, we introduce SubseasonalClimateUSA, a curated dataset for training and benchmarking subseasonal forecasting models in the United States. We use this dataset to benchmark a diverse suite of models, including operational dynamical models, classical meteorological baselines, and ten state-of-the-art machine learning and deep learning-based methods from the literature. Overall, our benchmarks suggest simple and effective ways to extend the accuracy of current operational models. SubseasonalClimateUSA is regularly updated and accessible via the https://github.com/microsoft/subseasonal_data/ Python package.